| |
|
 |
|
 |
|
|
|
| |
|
|
xen-users
Re: [Xen-users] Weird ram/dom-u limit problem
On 01/20/2010 05:26 PM, Fajar A. Nugraha wrote:
On Thu, Jan 21, 2010 at 2:20 AM, David Halik<dhalik@xxxxxxxxxxxxxxx> wrote:
I'm hitting what
*appears* to be some kind of wall on either the number of vm's or the amount
of ram they're using (personally I think it's ram, but I don't see how).
Number of vms can be very high (even over 300).
Ammount of ram is something you can easily see
loops = 64
are you using file:/ or tap:aio?
file. Is there any advantage to running tap over file? I know that the
driver is superior, and there is less chance of data loss, but we keep
our data on NFS, so I never really worried to much about it. file: seems
more manageable to me, but maybe tap is a better way to go? How is the
comparison in performance?
Now, if I attempt to install an 8th vm with 512MB or ram on either server
the install runs for awhile and then suddenly load on the xen server begins
to grow and grow and grow. Going from a load average: 0.09, 0.15, 0.10 to
load average: 10.58, 7.88, 4.70. The box itself begin to become very slow
and bogged down. top shows that it's because of cpu iowait, but I can't find
any particular reason for it.
try running "iostat -mx 3".
My guess is you're disk I/O bound.
I think you're right, I just came to the same conclusion. I moved the
install to a file on a second drive where the other vm's aren't mounted
and it worked *much* better. It seems like I'm going to have to do
installs on a seperate drive and then move the img over. The disk isn't
I/O bound when the vm's are doing normal work, so I'm only concerned
about install time.
--
================================
David Halik
System Administrator
OIT-CSS Rutgers University
dhalik@xxxxxxxxxxxxxxx
================================
_______________________________________________
Xen-users mailing list
Xen-users@xxxxxxxxxxxxxxxxxxx
http://lists.xensource.com/xen-users
|
|
|
| |
|
Home